]>
Commit | Line | Data |
---|---|---|
1 | ///////////////////////////////////////////////////////////////////////////// | |
2 | // Name: wx/encconv.h | |
3 | // Purpose: wxEncodingConverter class for converting between different | |
4 | // font encodings | |
5 | // Author: Vaclav Slavik | |
6 | // Copyright: (c) 1999 Vaclav Slavik | |
7 | // Licence: wxWindows licence | |
8 | ///////////////////////////////////////////////////////////////////////////// | |
9 | ||
10 | #ifndef _WX_ENCCONV_H_ | |
11 | #define _WX_ENCCONV_H_ | |
12 | ||
13 | #include "wx/defs.h" | |
14 | ||
15 | #include "wx/object.h" | |
16 | #include "wx/fontenc.h" | |
17 | #include "wx/dynarray.h" | |
18 | ||
19 | // ---------------------------------------------------------------------------- | |
20 | // constants | |
21 | // ---------------------------------------------------------------------------- | |
22 | ||
23 | enum | |
24 | { | |
25 | wxCONVERT_STRICT, | |
26 | wxCONVERT_SUBSTITUTE | |
27 | }; | |
28 | ||
29 | ||
30 | enum | |
31 | { | |
32 | wxPLATFORM_CURRENT = -1, | |
33 | ||
34 | wxPLATFORM_UNIX = 0, | |
35 | wxPLATFORM_WINDOWS, | |
36 | wxPLATFORM_OS2, | |
37 | wxPLATFORM_MAC | |
38 | }; | |
39 | ||
40 | // ---------------------------------------------------------------------------- | |
41 | // types | |
42 | // ---------------------------------------------------------------------------- | |
43 | ||
44 | WX_DEFINE_ARRAY_INT(wxFontEncoding, wxFontEncodingArray); | |
45 | ||
46 | //-------------------------------------------------------------------------------- | |
47 | // wxEncodingConverter | |
48 | // This class is capable of converting strings between any two | |
49 | // 8bit encodings/charsets. It can also convert from/to Unicode | |
50 | //-------------------------------------------------------------------------------- | |
51 | ||
52 | class WXDLLIMPEXP_BASE wxEncodingConverter : public wxObject | |
53 | { | |
54 | public: | |
55 | ||
56 | wxEncodingConverter(); | |
57 | virtual ~wxEncodingConverter() { if (m_Table) delete[] m_Table; } | |
58 | ||
59 | // Initialize conversion. Both output or input encoding may | |
60 | // be wxFONTENCODING_UNICODE, but only if wxUSE_WCHAR_T is set to 1. | |
61 | // | |
62 | // All subsequent calls to Convert() will interpret it's argument | |
63 | // as a string in input_enc encoding and will output string in | |
64 | // output_enc encoding. | |
65 | // | |
66 | // You must call this method before calling Convert. You may call | |
67 | // it more than once in order to switch to another conversion | |
68 | // | |
69 | // Method affects behaviour of Convert() in case input character | |
70 | // cannot be converted because it does not exist in output encoding: | |
71 | // wxCONVERT_STRICT -- | |
72 | // follow behaviour of GNU Recode - just copy unconvertable | |
73 | // characters to output and don't change them (it's integer | |
74 | // value will stay the same) | |
75 | // wxCONVERT_SUBSTITUTE -- | |
76 | // try some (lossy) substitutions - e.g. replace | |
77 | // unconvertable latin capitals with acute by ordinary | |
78 | // capitals, replace en-dash or em-dash by '-' etc. | |
79 | // both modes gurantee that output string will have same length | |
80 | // as input string | |
81 | // | |
82 | // Returns false if given conversion is impossible, true otherwise | |
83 | // (conversion may be impossible either if you try to convert | |
84 | // to Unicode with non-Unicode build of wxWidgets or if input | |
85 | // or output encoding is not supported.) | |
86 | bool Init(wxFontEncoding input_enc, wxFontEncoding output_enc, int method = wxCONVERT_STRICT); | |
87 | ||
88 | // Convert input string according to settings passed to Init. | |
89 | // Note that you must call Init before using Convert! | |
90 | bool Convert(const char* input, char* output) const; | |
91 | bool Convert(char* str) const { return Convert(str, str); } | |
92 | wxString Convert(const wxString& input) const; | |
93 | ||
94 | #if wxUSE_WCHAR_T | |
95 | bool Convert(const char* input, wchar_t* output) const; | |
96 | bool Convert(const wchar_t* input, char* output) const; | |
97 | bool Convert(const wchar_t* input, wchar_t* output) const; | |
98 | bool Convert(wchar_t* str) const { return Convert(str, str); } | |
99 | #endif | |
100 | // Return equivalent(s) for given font that are used | |
101 | // under given platform. wxPLATFORM_CURRENT means the plaform | |
102 | // this binary was compiled for | |
103 | // | |
104 | // Examples: | |
105 | // current platform enc returned value | |
106 | // ----------------------------------------------------- | |
107 | // unix CP1250 {ISO8859_2} | |
108 | // unix ISO8859_2 {} | |
109 | // windows ISO8859_2 {CP1250} | |
110 | // | |
111 | // Equivalence is defined in terms of convertibility: | |
112 | // 2 encodings are equivalent if you can convert text between | |
113 | // then without loosing information (it may - and will - happen | |
114 | // that you loose special chars like quotation marks or em-dashes | |
115 | // but you shouldn't loose any diacritics and language-specific | |
116 | // characters when converting between equivalent encodings). | |
117 | // | |
118 | // Convert() method is not limited to converting between | |
119 | // equivalent encodings, it can convert between arbitrary | |
120 | // two encodings! | |
121 | // | |
122 | // Remember that this function does _NOT_ check for presence of | |
123 | // fonts in system. It only tells you what are most suitable | |
124 | // encodings. (It usually returns only one encoding) | |
125 | // | |
126 | // Note that argument enc itself may be present in returned array! | |
127 | // (so that you can -- as a side effect -- detect whether the | |
128 | // encoding is native for this platform or not) | |
129 | static wxFontEncodingArray GetPlatformEquivalents(wxFontEncoding enc, int platform = wxPLATFORM_CURRENT); | |
130 | ||
131 | // Similar to GetPlatformEquivalent, but this one will return ALL | |
132 | // equivalent encodings, regardless the platform, including itself. | |
133 | static wxFontEncodingArray GetAllEquivalents(wxFontEncoding enc); | |
134 | ||
135 | // Return true if [any text in] one multibyte encoding can be | |
136 | // converted to another one losslessly. | |
137 | // | |
138 | // Do not call this with wxFONTENCODING_UNICODE, it doesn't make | |
139 | // sense (always works in one sense and always depends on the text | |
140 | // to convert in the other) | |
141 | static bool CanConvert(wxFontEncoding encIn, wxFontEncoding encOut) | |
142 | { | |
143 | return GetAllEquivalents(encIn).Index(encOut) != wxNOT_FOUND; | |
144 | } | |
145 | ||
146 | private: | |
147 | ||
148 | #if wxUSE_WCHAR_T | |
149 | wchar_t *m_Table; | |
150 | #else | |
151 | char *m_Table; | |
152 | #endif | |
153 | bool m_UnicodeInput, m_UnicodeOutput; | |
154 | bool m_JustCopy; | |
155 | ||
156 | wxDECLARE_NO_COPY_CLASS(wxEncodingConverter); | |
157 | }; | |
158 | ||
159 | #endif // _WX_ENCCONV_H_ |